35results about How to "Implement anomaly detection" patented technology

The invention discloses an ocean internal wave monitoring method based on deep learning, which belongs to the technical field of ocean internal wave monitoring, is used for ocean internal wave monitoring, and comprises the following steps: acquiring a flow velocity data set of an observed sea area, taking the flow velocity data set as an original data set, performing quality control on the original data set, and performing normal sequence and abnormal sequence distinguishing on the data after quality control. Dividing a training set, a verification set and a test set; constructing an ocean internal wave anomaly monitoring model, optimizing anomaly scores and reconstructing error parameters, monitoring flow velocity observation data of the sea area by using the trained ocean internal wave anomaly monitoring model, and identifying an ocean internal wave sequence; and performing internal wave mechanical characteristic analysis on the ocean internal wave sequence extracted by the ocean internal wave anomaly monitoring model, and outputting characteristics. According to the method, the behavior pattern of the normal flow velocity can be accurately captured by adopting the deep learning model, the anomaly detection of the internal wave flow is realized through the reconstruction error, the normal flow velocity and the internal wave flow velocity are effectively distinguished, and misjudgment and missed judgment caused by a traditional method are reduced.

The invention belongs to the technical field of mine transportation, and discloses a belt conveyor roller anomaly detection system based on optical fiber auscultation, which comprises a data acquisition unit, a preprocessing unit and a prediction model which are connected in sequence, and an anomaly detection unit and a linear layer which are connected with the prediction model. The data acquisition unit acquires audio data in the running process of the carrier roller, converts the audio data into vibration data and outputs the vibration data to the preprocessing unit, the preprocessing unit segments the input vibration data, the segmented vibration data are input into the trained prediction model, and the prediction model is used for predicting the carrier roller. And the prediction model outputs the characteristics of the potential space corresponding to the current vibration data to an anomaly detection unit, the distance between the characteristics of the current potential space and the characteristic center of the potential space when the carrier roller normally operates is calculated, and if the distance is larger than a set distance threshold value, the current operation of the corresponding section of carrier roller is abnormal. According to the method, automatic detection of the abnormity of the carrier roller is realized, the information contained in the potential spatial features output by the prediction model is richer, and the abnormity detection precision of the carrier roller is improved.

The invention discloses an intelligent beam field construction management system based on BIM and GIS, and relates to the technical field of beam field construction management. Main parameters of a beam field construction environment can be fully covered by deploying a temperature and humidity sensor, an air quality sensor, a noise sensor, a wind speed and direction sensor and a rainfall sensor; spatial data association is performed on the BIM model by using a spatial analysis tool in a GIS platform, geographic information and construction in the BIM model are subjected to geographic space matching, and the accuracy of an association result is ensured through verification, so that data integration and sharing are facilitated, the use efficiency of the data is improved, and the method is suitable for popularization and application. A construction supervisor can monitor the construction progress according to the tracking data recorded in real time, a construction plan is adjusted in time, and smooth construction is ensured.

The invention discloses a boiler state intelligent monitoring method and device and electronic equipment, and the method comprises the steps: collecting a to-be-processed data set in the operation process of a target boiler in real time; based on a pre-constructed target prediction model, performing prediction processing on the real-time input data at each data acquisition moment to obtain prediction output data corresponding to each data acquisition moment; determining a target residual error corresponding to the to-be-processed data group according to the real-time output data and the predicted output data corresponding to each data acquisition moment; and according to the target residual error and the target comparison threshold interval corresponding to the target residual error, the operation state of the target boiler is determined. According to the invention, the operation state of the boiler is automatically subjected to anomaly detection, so that the detection efficiency and the detection accuracy are improved, and the abnormal operation state of the boiler is found in time.

The invention discloses a camera anomaly detection method, electronic equipment and a storage device, and the method comprises the steps: employing a camera of a to-be-detected vehicle in a target scene to carry out the collection of target identifiers matched with a plurality of target stations, and obtaining the collection positions of the target identifiers in a map coordinate system; based on the collection position and a reference position corresponding to the target identifier in the map coordinate system, obtaining a position deviation matched with the target identifier; based on the position deviation, deviation probability distribution matched with the to-be-detected vehicle is obtained; based on the deviation probability distribution and the reference probability distribution, obtaining a camera detection result matched with the to-be-detected vehicle; wherein the reference probability distribution is determined based on deviation probability distribution matched with a plurality of reference vehicles in the target scene. In this way, the accuracy of camera detection can be improved.

The embodiment of the invention discloses a data message detection method and device, equipment and a storage medium, and the method comprises the steps: positioning a data load in a detection message, and obtaining a target number of bytes from a current detection point of the data load as a comparison index; matching the comparison index with a target comparison table constructed according to the previous target number of bytes of each feature code; if the comparison index hits the target comparison table, obtaining a comparison field matched with the hit target feature code from the current check point, and matching the comparison field with the target feature code; if the comparison field is successfully matched with the target feature code, abnormal prompting is carried out on the detection message; and if the comparison index does not hit the target comparison table or the comparison field is not matched with the target feature code, after a new current detection point is determined, returning to execute the operation of acquiring the target number of bytes as the comparison index from the current detection point of the data load until the detection of all the data loads is completed, so that the accuracy of the detection result is improved.

The invention provides an AI application anomaly detection method, electronic equipment, a storage medium and a program product, and belongs to the technical field of artificial intelligence. The method comprises the steps that the target execution time length of an API calling sequence is obtained, the API calling sequence refers to a periodic sequence formed by APIs in a hijacking library according to a calling sequence when an AI application provides target service, the hijacking library is used for hijacking calling instructions of the AI application for APIs in a dynamic link library, the hijacking library and the dynamic link library have the same API, and the target execution time length of the API calling sequence is obtained; the target execution duration is the execution duration of the API calling sequence when the AI application provides any target service; obtaining a reference execution time length of the API calling sequence, wherein the reference execution time length is an execution time length of the API calling sequence when the AI application provides a target service once in a normal state; and when the target execution duration exceeds the reference execution duration, determining that the AI application is in an abnormal state. According to the method, the AI application exception can be detected based on the API calling sequence.

The invention relates to the technical field of encrypted traffic of a large-scale data set, in particular to an encrypted traffic anomaly detection method and system based on an attention mechanism. Obtaining packet data, and carrying out data preprocessing to obtain preprocessed data; constructing an auto-encoder model, wherein the auto-encoder model comprises a multi-head attention mechanism enhanced bidirectional gating cycle unit encoding layer and a self-attention mechanism enhanced bidirectional long-short-term memory network decoding layer; and carrying out encryption traffic anomaly detection on the preprocessed data by using the auto-encoder model. The multi-head attention mechanism enhanced bidirectional gating circulation unit and the self-attention mechanism enhanced bidirectional long-short-term memory network are creatively combined, so that the time sequence characteristics are effectively extracted, and the front-back relevance of the sequence data is kept. Meanwhile, model training is carried out by adopting a composite loss function containing business associated loss, and the generalization ability of the model is improved by combining cross validation and regularization technologies.

The invention belongs to the technical field related to bearing abnormity, and discloses a construction method and system of a rolling bearing abnormity detection model. The method comprises the following steps: collecting vibration signals of bearing vibration to form an original vibration signal set A, and endowing a fault label with the original vibration signal set A; performing data processing on the original vibration signal set by using the data generation model to generate a new vibration signal, and forming a new vibration signal set B; the vibration signals in the vibration signal set B and the vibration signals in the original vibration signal set A are spliced to form spliced vibration signals, the fault labels of the spliced vibration signals are the same as the vibration signals in the vibration signal set B, and the spliced vibration signals are added to the original vibration signal set A to form a vibration signal set C; the vibration signal set C is used for training an anomaly detection model to obtain a needed anomaly detection model of the rolling bearing, the input of the anomaly detection model is vibration signals, and the output of the anomaly detection model is a fault label. According to the invention, the technical problem of difficulty in bearing abnormity detection is solved.

The invention relates to a network security monitoring method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring a first network entity relation graph and a second network entity relation graph according to multi-source log data of a to-be-monitored network environment; the first network entity relation graph is used for representing a direct interaction relation between network entities of different or the same entity type in the network environment to be monitored; the second network entity relation graph is used for representing a dependency interaction relation between network entities of the same or different entity types in the network environment to be monitored; fusing the first network entity relation graph and the second network entity relation graph to obtain a fused entity relation graph; and according to the graph node feature vector representation corresponding to the node in the fused entity relation graph, identifying an abnormal event type corresponding to the abnormal sub-graph in the fused entity relation graph. By adopting the method, the accuracy of network security monitoring can be improved.

The present invention belongs to the field of data analysis technology, and relates to a method, device and medium for detecting anomalies of power time series data based on a large model, wherein the method comprises the following steps: inputting the power time series data to be detected into a trained power time series data anomaly detection model, and outputting the detection result; the power time series data anomaly detection model comprises a wavelet decomposition module, an encoder module and a decoder module connected in sequence, wherein the wavelet decomposition module first performs wavelet decomposition on the power time series data, and then converts each component sequence into a feature representation of equal length through multi-head self-attention; the decoder module calculates the dynamic time warping distance between the output of the encoder module and each historical candidate mode in a differentiable manner, and calculates the contribution score of each historical candidate mode accordingly, and aggregates to obtain the feature representation of the power time series data at each period scale, and outputs it through an inverse wavelet transform. Compared with the prior art, the present invention can improve the accuracy of the anomaly detection results of power time series data.

The present invention provides a cable loosening identification method based on data processing. The method responds to a loosening identification request, determines a comprehensive pre-inspection path according to the cable properties of a target cable, performs image acquisition on the upper surface of the target cable based on the comprehensive pre-inspection path, and obtains a plurality of pre-inspection acquisition images; performs multi-dimensional anomaly recognition on the pre-inspection acquisition image according to a loosening anomaly recognition strategy, and obtains an abnormal acquisition image corresponding to a corresponding upward-looking hovering point; sequentially counts downward-looking hovering points corresponding to the lower surface of the target cable based on the abnormal acquisition image, obtains an abnormal focusing path, and acquires an abnormal acquisition image corresponding to the abnormal focusing path; calculates the abnormality ratio in the abnormal acquisition image, obtains a loosening analysis value corresponding to the target cable, and determines a loosening identification result of the target cable based on the loosening analysis value.

The invention discloses an anomaly detection method and device and electronic equipment, and belongs to the technical field of terminals. The anomaly detection method comprises the steps of performing anomaly detection on a fingerprint module under the condition that fingerprint service related conditions are met; wherein the fingerprint service related condition is used for triggering the fingerprint module to execute or end execution of at least one service.

The present invention discloses a prediction reconstruction video anomaly detection method integrating latent space autoregression, which belongs to the field of surveillance video processing, and solves the video anomaly misdetection and missed detection problems caused by the diversity of video information and the scarcity of abnormal events in traditional methods; including firstly performing data preprocessing on the input video sequence by random cropping, random horizontal rotation and standardization operation; defining prediction network constraints, generating prediction frames that meet the constraints; then constructing a reconstruction network in combination with a UNet network and a latent space autoregressive layer, generating a reconstruction frame that meets the constraints; then constructing a discriminator by stacking multiple convolutional layers to discriminate the abnormal values ​​of the input frame; finally adopting a generative adversarial algorithm, training the prediction generation network, the reconstruction network and the discriminator, and optimizing the network parameters. The recognition accuracy obtained by the present invention is relatively high, and the recognition speed is relatively fast, which can meet the real-time requirements of video anomaly detection in large-scale surveillance scenarios.

The invention relates to a diagnosis positioning method, device and equipment for dynamic memory release abnormity and a medium, and the method comprises the steps that a dynamic link library is customized, an environment variable of a to-be-detected application program points to a path of the dynamic link library, and the dynamic link library comprises a memory distribution function and a memory release function; and running the to-be-detected application program, calling the dynamic link library through a dynamic memory interface, positioning a dynamic memory release exceptional code, and outputting a positioning result. The dynamic memory allocation and release of the to-be-detected application program are realized by adopting the dynamic link library, so that the code reusability of the dynamic link library is high, the compiling modification of the to-be-detected application program is avoided, the exception detection in the memory allocation and release process is realized, and the method and the device can adapt to various application scenes, and are convenient to use. And the flexibility of dynamic memory release anomaly detection is improved.

The present invention relates to the field of intelligent unmanned boats, and in particular to a path optimization method and system for intelligent unmanned boats, which are used to solve the problem that the existing intelligent unmanned boats are unable to perform abnormality detection and real-time path optimization, resulting in the inability of the intelligent unmanned boats to perform efficient, accurate and safe operations in a complex and changeable marine environment; the system realizes abnormality detection of the unmanned boat, effectively reduces the risk of failure of the unmanned boat during the execution of the mission, ensures the continuous and stable operation of the unmanned boat, improves the safety and reliability of the mission execution, and can also dynamically adjust the navigation path, actively avoid danger, and automatically plan a safe and efficient driving route, thereby improving the operating safety and reliability of the unmanned boat, gradually improving its prediction accuracy of future road conditions and path adaptability, and further enhancing the operation capability of the intelligent unmanned boat in a complex and changeable environment.

The invention relates to the field of intelligent power consumption management, and discloses an intelligent detection method, device and equipment based on electric energy meters and a storage medium, and the method comprises the steps: obtaining to-be-detected key data of each electric energy meter, carrying out the generation of a detection matrix according to the to-be-detected key data of each electric energy meter, obtaining an electric quantity detection matrix, and carrying out the calculation of the electric quantity detection matrix according to the electric quantity detection matrix, carrying out first parameter calculation to obtain an electric quantity difference value, carrying out second parameter calculation according to the electric quantity detection matrix to obtain a charging coefficient, carrying out third parameter calculation according to the electric quantity detection matrix to obtain an electric quantity sufficient period, and carrying out fourth parameter calculation according to the electric quantity detection matrix to obtain an electricity utilization fluctuation coefficient; and according to the electric quantity difference value, the charging coefficient, the electric quantity sufficient period and the power utilization fluctuation coefficient, whether the electric energy meter is abnormal or not is judged based on an anomaly detection function. The method can realize anomaly detection of the electric energy meter.

The invention discloses a fault detection and classification method for an energy storage battery and a storage medium, and the method comprises the steps: completing the unsupervised anomaly detection through the normal operation data, obtaining the fault features of the abnormal data for the obtained abnormal data, and completing the classification of the features; and after the abnormity is triggered, calling a supervised classification model to give a fault type probability. A computer program used for executing the method is stored in the storage medium. The method has the advantages of simple principle, easiness in implementation, wide application range and the like.

The application relates to the technical field of crack detection, and discloses a cement pouring surface crack detection method and system, which comprises the following steps: a high-frequency sound wave is emitted to a cement pouring surface structure by using an ultrasonic instrument; when the sound wave meets the cement pouring surface, a reflection is generated to form an echo; the echo is captured by a receiver; and whether the cement pouring surface has cracks and the depth of the cracks is identified according to the time difference of the echo. The application continuously captures crack echoes of a preset data detection amount, carries out peak amplitude sorting and difference value calculation on all captured echo segment signals, and further judges whether there is an abnormal echo fluctuation by comparing the fluctuation amplitudes, so that the double judgment mechanism can more effectively exclude invalid scattering and redundant reflection signals caused by rough cement pouring surfaces and other factors, and the risk of misjudgment or false crack alarm is greatly reduced.

The application discloses a lottery ticket device and a running method thereof. The lottery ticket device comprises a shell forming a paper running channel, a transparent plate arranged at an observation window, a camera for image acquisition, a rubber roller device for conveying paper, a ticket feeding sensor and a position sensing assembly for detecting a paper feeding state, a marking device for marking paper feeding, and a controller. The controller performs unified image acquisition and identification processing on a handwritten betting slip, a computer ticket and an instant ticket through the camera, and controls the marking device to perform printing marking or punching marking according to an identification result. The running method comprises paper feeding detection, image acquisition, type determination and corresponding processing flow. Through the adaptive adjustment structure of the paper feeding channel, the single-camera image identification and the collaborative design of the single-module double-marking structure, the application realizes the integrated operation of automatic identification, classification processing and marking of multiple types of tickets, and significantly improves the processing efficiency while simplifying the equipment structure.

The application discloses a Deepfake video detection method based on multi-domain feature region standard score difference, which comprises the following steps: data set division; video frame division and extraction of a region to be detected; construction of a double-branch convolutional neural network; calculation of the RGB feature and NSCT sub-band image of the region to be detected; frequency domain feature obtained by frequency band fusion of the NSCT sub-band image; response of different level texture features obtained through a texture feature extraction module; output features of the space domain and frequency domain feature branches are spliced along the channel dimension, and input into an abnormal feature discrimination module to obtain a tampered region prediction mask; the tampered region prediction mask is subjected to a full connection layer to obtain one-dimensional features, which are spliced with the output features of the texture feature extraction module, and then subjected to a full connection layer and a Softmax activation function to output a binary classification prediction result. The application can better combine the feature information of the space domain and the frequency domain, strengthen the response to the texture feature, discriminate abnormal tampering traces, and improve the generalization ability of the model.

According to the external equipment anomaly detection method and device, the electronic equipment and the storage medium provided by the embodiment of the invention, each established peripheral driving module in the technical scheme can support conversion of the heartbeat packet for detecting the anomaly of the external equipment into the protocol heartbeat packet corresponding to the included communication protocol, and the protocol heartbeat packet is sent to the external equipment; according to the embodiment of the invention, the method achieves the anomaly detection of the external equipment with different communication protocols, effectively solves a problem that the conventional embedded equipment cannot carry out the anomaly detection of the external equipment which is not consistent with the communication protocol of the conventional embedded equipment, and brings inconvenience to a user, and greatly improves the use experience of the user.

The utility model provides an LCD (liquid crystal display) pin mucilage glue detection device, which belongs to the technical field of detection devices, and comprises a fixing platform, a detection platform, a detection platform, a detection platform, a detection platform and a control device, and is characterized in that the fixing platform is used for fixing an LCD; the test board is used for testing on-off of a circuit and is arranged below the fixed table, and the surface of the test board is provided with connecting blocks connected with the metal pins; and when the LCD is placed on the fixed table, the connecting blocks are over against the inner side surfaces of the metal pins. The LCD is fixed through the fixing table, the testing plate is arranged below the fixing table, the connecting block on the testing plate is right opposite to the inner side face of the metal pin, and the connecting block detects on-off of the inner side face of the metal pin by making contact with the inner side face of the metal pin, so that detection of viscose glue on the inner side face of the metal pin of the LCD is achieved. When the device is used for carrying out adhesive detection on the LCD pin, the detection efficiency of the LCD pin can be effectively improved, the missing detection of the LCD pin is avoided, and the abnormity detection of the inner side surface of the metal pin of the LCD can be realized.

The present invention relates to the field of data processing, and more specifically, to a data processing method for a drug database, the method comprising: obtaining a drug data set, wherein the drug data set includes a plurality of drug data; obtaining preset neighborhood data of any drug data; clustering the neighborhood data into a plurality of clusters; calculating the reference weight of each neighborhood data; using the reference weight of each neighborhood data as the weight, using the LOF algorithm to calculate the local reachable density of the drug data; and using the LOF algorithm to perform anomaly detection based on the local reachable density to remove the abnormal data in the drug database. By analyzing the degree to which the drug data and each neighborhood data belong to the same category, different weights are set for each neighborhood data to improve the accuracy of anomaly detection.

The invention relates to a channel detection method and device, a computer program product and electronic equipment, and relates to the technical field of network and information security, the method comprises the following steps: obtaining session metadata and network flow data, and aggregating the session metadata to obtain grouped metadata; screening the grouped metadata to obtain target grouped metadata, and determining a first vector corresponding to session metadata included in the target grouped metadata; retrieving in the network traffic data according to the target packet metadata to obtain target network traffic data, and generating a second vector corresponding to the target network traffic data; and generating a splicing vector according to the first vector and the second vector, obtaining a central point of the splicing vector and a standard deviation of a distance to the central point, and obtaining a detection result of the network channel corresponding to the network request based on the standard deviation. According to the invention, the problems that the HTTP covert channel detection method is easy to bypass and the training sample is difficult to construct are solved.

The invention discloses a protection circuit and a protection method of a protected module, a storage medium and electronic equipment. The protection circuit of the protected module comprises a first detection control module which is configured to determine the current state of the protected module based on a transmission signal on a control signal bus between a real control signal source and the protected module; the generation module is configured to generate test input data in response to the fact that the current state is the idle state; and the second detection control module is configured to determine an anomaly detection result of the protected module based on actual test output data output by the protected module for the test input data and expected test output data corresponding to the test input data. According to the embodiment of the invention, the anomaly detection of the protected module can be effectively realized on the premise that the normal work of the protected module is not influenced.

The utility model discloses a radio frequency self -checking device for FDD microwave communication system, including coupling circuit, frequency conversion circuit, frequency source circuit and controller, the coupling circuit is equipped with a two -way radio frequency port for with the two -way connection of external duplexer's tuning terminal, the through output port of coupling circuit is connected with the radio frequency input port of frequency conversion circuit, the intermediate frequency output port of frequency conversion circuit is connected with the coupling input port of coupling circuit, the local oscillator port of frequency conversion circuit is connected with the output port of frequency source circuit, it belongs to communication field, through this self -checking device, the signal of transmitting channel in system is frequency conversion to the signal of receiving channel, and sends back receiving channel and carries out the signal processing effect.

The present invention discloses a method for detecting abnormal fluctuations in battery production processes based on deep learning. The present invention proposes a DAUAD model, which combines the powerful reconstruction and feature extraction capabilities of the autoencoder. In order to improve the stability of the latent space expression vector of the input sample, the present invention adds an Encoder_g module to encode the reconstructed sample, so that the latent space expression of the input sample and the latent space vector expression of the reconstructed sample are as close as possible, thereby improving the stability of the latent expression space vector. The problem that the autoencoder cannot obtain the key information of the input sample during the feature extraction process is effectively solved, and the GUR network is used to consider the impact of the past battery production process on the present, and finally realize the abnormal detection of multi-dimensional time series in the battery production process.

The present application relates to the field of computer technology, and in particular to a log statement collection method, anomaly detection method and system, and related devices. The log statement collection method includes: obtaining a log method in the source code of a target system, screening an associated method in the source code of the target system that is associated with the obtained log method; based on the associated method and the log method, collecting log statements of the target system; serializing the log statements to obtain log sequences, and assigning category labels to the log sequences; wherein the log sequence categories are associated with the target system analysis requirements. The use of this method can collect the computational burden of log statements in the source code and is conducive to improving the comprehensiveness of the collection, thereby realizing anomaly detection of the storage system based on the operation log of the storage system.